AI tool to predict hospital-acquired infections using health records

Predicting Hospital-Acquired Infections Using Electronic Health Records: An AI-Assisted Approach

This study is testing an AI tool that looks at health records to see if it can help doctors spot hospital-acquired infections earlier and keep patients safer.

Quick facts

• Study type: Observational
• Enrollment: 1000000 (estimated)
• Ages: 0 Years to 90 Years
• Sex: All
• Sponsor: The Eye Hospital of Wenzhou Medical University (Academic / other)
• Locations: 2 sites (Wenzhou, Zhejiang and 1 other locations)
• Trial ID: NCT06791382 on ClinicalTrials.gov

What this trial studies

This observational study evaluates an AI-assisted predictive model designed to identify and diagnose hospital-acquired infections (HAIs) by analyzing multimodal health data from electronic health records (EHR). The study aims to enhance early identification of patients at risk for HAIs by integrating various data sources, including medical history, lab results, and clinical observations. By improving the accuracy and efficiency of infection prediction, the study seeks to streamline clinical workflows and optimize infection control measures, ultimately aiming to reduce the incidence of HAIs and improve patient safety.

Who should consider this trial

Good fit: Ideal candidates include hospitalized patients with complete and accessible EHR data who can provide informed consent.

Not a fit: Patients with incomplete EHR data, severe cognitive disorders, or those not admitted to the hospital during the study period may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could significantly reduce the incidence of hospital-acquired infections, leading to better patient outcomes and lower healthcare costs.

How similar studies have performed: While the application of AI in predicting infections is a growing field, this specific approach integrating multimodal EHR data is relatively novel and has not been extensively tested.

Eligibility criteria

Inclusion Criteria:

1. Patients with complete and accessible EHR data, including medical history, laboratory test results, treatment regimens, clinical observations, and infection history.
2. Patients who have been admitted to the participating hospital or healthcare facility during the study period.
3. All participants must provide informed consent to use their health data for research purposes.

Exclusion Criteria:

1. Patients with incomplete or missing critical EHR data, such as lab results, medical history, or treatment details, which are necessary for infection prediction.
2. Patients who have severe cognitive disorders, dementia, or conditions that prevent them from providing informed consent or participating in the study.
3. Patients who have not been admitted to the hospital during the study period or who are receiving outpatient care only.
4. Patients with terminal conditions where infection prediction may not be applicable to the clinical goals of the study.

Where this trial is running

Wenzhou, Zhejiang and 1 other locations

• First Affiliated Hospital of Wenzhou Medical University — Wenzhou, Zhejiang, China (Recruiting)
• Second Affiliated Hospital of Wenzhou Medical University — Wenzhou, Zhejiang, China (Recruiting)

Study contacts

• Study coordinator: Fei Liu, MD

Conditions Hospital-acquired Infections